├── README.md ├── .github └── workflows │ └── main.yml ├── traffic.ipynb └── LICENSE /README.md: -------------------------------------------------------------------------------- 1 | # AWS Glue Pipeline Example 2 | 3 | This repository shows an example CI/CD pipeline using GitHub Actions for doing continuous 4 | deployment of AWS Glue jobs built on PySpark and Jupyter Notebooks. This is for 5 | demonstration purposes only. 6 | 7 | See this [blog post](https://blog.realkinetic.com/continuous-deployment-for-aws-glue-c8abd50d7d58) 8 | for more information. 9 | -------------------------------------------------------------------------------- /.github/workflows/main.yml: -------------------------------------------------------------------------------- 1 | name: build-and-deploy 2 | 3 | # Controls when the action will run. Triggers the workflow on push 4 | # but only for the master branch. 5 | on: 6 | push: 7 | branches: [ master ] 8 | 9 | # A workflow run is made up of one or more jobs that can run sequentially or in parallel 10 | jobs: 11 | # This workflow contains two jobs called "build" and "deploy" 12 | build: 13 | # The type of runner that the job will run on 14 | runs-on: ubuntu-latest 15 | 16 | # Steps represent a sequence of tasks that will be executed as part of the job 17 | steps: 18 | # Checks-out your repository under $GITHUB_WORKSPACE, so your job can access it 19 | - uses: actions/checkout@v2 20 | 21 | # Set up Python 22 | - name: Set up Python 3.8 23 | uses: actions/setup-python@v2 24 | with: 25 | python-version: '3.8' 26 | 27 | # Install nbconvert to convert notebook file to python script 28 | - name: Install nbconvert 29 | run: | 30 | python -m pip install --upgrade pip 31 | pip install nbconvert 32 | 33 | # Convert notebook file to python 34 | - name: Convert notebook 35 | run: jupyter nbconvert --to python traffic.ipynb 36 | 37 | # Persist python script for use between jobs 38 | - name: Upload python script 39 | uses: actions/upload-artifact@v2 40 | with: 41 | name: traffic.py 42 | path: traffic.py 43 | 44 | # Upload python script to S3 and update Glue job 45 | deploy: 46 | needs: build 47 | runs-on: ubuntu-latest 48 | steps: 49 | - name: Download python script from build 50 | uses: actions/download-artifact@v2 51 | with: 52 | name: traffic.py 53 | 54 | # Install the AWS CLI 55 | - name: Install AWS CLI 56 | run: | 57 | curl "https://awscli.amazonaws.com/awscli-exe-linux-x86_64.zip" -o "awscliv2.zip" 58 | unzip awscliv2.zip 59 | sudo ./aws/install 60 | 61 | # Set up credentials used by AWS CLI 62 | - name: Set up AWS credentials 63 | shell: bash 64 | env: 65 | AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }} 66 | AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }} 67 | run: | 68 | mkdir -p ~/.aws 69 | touch ~/.aws/credentials 70 | echo "[default] 71 | aws_access_key_id = $AWS_ACCESS_KEY_ID 72 | aws_secret_access_key = $AWS_SECRET_ACCESS_KEY" > ~/.aws/credentials 73 | 74 | # Copy the file to the S3 bucket 75 | - name: Upload to S3 76 | run: aws s3 cp traffic.py s3://${{secrets.S3_BUCKET}}/traffic_${GITHUB_SHA}.py --region us-east-1 77 | 78 | # Update the Glue job to use the new script 79 | - name: Update Glue job 80 | run: | 81 | aws glue update-job --job-name "Traffic ETL" --job-update \ 82 | "Role=AWSGlueServiceRole-TrafficCrawler,Command={Name=glueetl,ScriptLocation=s3://${{secrets.S3_BUCKET}}/traffic_${GITHUB_SHA}.py},Connections={Connections=redshift}" \ 83 | --region us-east-1 84 | 85 | # Remove stored credentials file 86 | - name: Cleanup 87 | run: rm -rf ~/.aws 88 | 89 | -------------------------------------------------------------------------------- /traffic.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "metadata": {}, 6 | "source": [ 7 | "# Traffic Data ETL Demo\n", 8 | "\n", 9 | "This is a demo ETL process that extracts traffic data stored as CSV in S3, transforms it, and loads it into Redshift.\n", 10 | "\n", 11 | "## Boilerplate" 12 | ] 13 | }, 14 | { 15 | "cell_type": "code", 16 | "execution_count": 72, 17 | "metadata": {}, 18 | "outputs": [ 19 | { 20 | "data": { 21 | "application/vnd.jupyter.widget-view+json": { 22 | "model_id": "", 23 | "version_major": 2, 24 | "version_minor": 0 25 | }, 26 | "text/plain": [ 27 | "FloatProgress(value=0.0, bar_style='info', description='Progress:', layout=Layout(height='25px', width='50%'),…" 28 | ] 29 | }, 30 | "metadata": {}, 31 | "output_type": "display_data" 32 | } 33 | ], 34 | "source": [ 35 | "from awsglue.transforms import *\n", 36 | "from awsglue.utils import getResolvedOptions\n", 37 | "from pyspark.context import SparkContext\n", 38 | "from awsglue.context import GlueContext\n", 39 | "from awsglue.job import Job\n", 40 | "\n", 41 | "glueContext = GlueContext(SparkContext.getOrCreate())" 42 | ] 43 | }, 44 | { 45 | "cell_type": "markdown", 46 | "metadata": {}, 47 | "source": [ 48 | "## Load the data source" 49 | ] 50 | }, 51 | { 52 | "cell_type": "code", 53 | "execution_count": 100, 54 | "metadata": {}, 55 | "outputs": [ 56 | { 57 | "data": { 58 | "application/vnd.jupyter.widget-view+json": { 59 | "model_id": "", 60 | "version_major": 2, 61 | "version_minor": 0 62 | }, 63 | "text/plain": [ 64 | "FloatProgress(value=0.0, bar_style='info', description='Progress:', layout=Layout(height='25px', width='50%'),…" 65 | ] 66 | }, 67 | "metadata": {}, 68 | "output_type": "display_data" 69 | } 70 | ], 71 | "source": [ 72 | "traffic = glueContext.create_dynamic_frame.from_catalog(\n", 73 | " database = \"traffic\",\n", 74 | " table_name = \"traffic\"\n", 75 | ")" 76 | ] 77 | }, 78 | { 79 | "cell_type": "markdown", 80 | "metadata": {}, 81 | "source": [ 82 | "## Drop unwanted fields" 83 | ] 84 | }, 85 | { 86 | "cell_type": "code", 87 | "execution_count": 101, 88 | "metadata": {}, 89 | "outputs": [ 90 | { 91 | "data": { 92 | "application/vnd.jupyter.widget-view+json": { 93 | "model_id": "", 94 | "version_major": 2, 95 | "version_minor": 0 96 | }, 97 | "text/plain": [ 98 | "FloatProgress(value=0.0, bar_style='info', description='Progress:', layout=Layout(height='25px', width='50%'),…" 99 | ] 100 | }, 101 | "metadata": {}, 102 | "output_type": "display_data" 103 | } 104 | ], 105 | "source": [ 106 | "traffic = traffic.drop_fields([\n", 107 | " 'location',\n", 108 | " 'boundaries - zip codes',\n", 109 | " 'community areas',\n", 110 | " 'census tracts',\n", 111 | " 'wards',\n", 112 | " ':@computed_region_awaf_s7ux'\n", 113 | "])" 114 | ] 115 | }, 116 | { 117 | "cell_type": "markdown", 118 | "metadata": {}, 119 | "source": [ 120 | "## Map remaining fields" 121 | ] 122 | }, 123 | { 124 | "cell_type": "code", 125 | "execution_count": 102, 126 | "metadata": {}, 127 | "outputs": [ 128 | { 129 | "data": { 130 | "application/vnd.jupyter.widget-view+json": { 131 | "model_id": "", 132 | "version_major": 2, 133 | "version_minor": 0 134 | }, 135 | "text/plain": [ 136 | "FloatProgress(value=0.0, bar_style='info', description='Progress:', layout=Layout(height='25px', width='50%'),…" 137 | ] 138 | }, 139 | "metadata": {}, 140 | "output_type": "display_data" 141 | } 142 | ], 143 | "source": [ 144 | "def reformat_date(record):\n", 145 | " \"\"\"Change 'date of count' format from mm/dd/yyyy to yyyy-mm-dd.\"\"\"\n", 146 | " date = record['date of count']\n", 147 | " month, day, year = date.split('/')\n", 148 | " record['date of count'] = year + '-' + month + '-' + day\n", 149 | " return record\n", 150 | "\n", 151 | "def split_vehicle_volume(record):\n", 152 | " \"\"\"Split 'vehicle volume by each direction of traffic' into\n", 153 | " separate fields for each direction.\n", 154 | " \"\"\"\n", 155 | " volumes = record['vehicle volume by each direction of traffic']\n", 156 | " direction_volumes = volumes.split('/')\n", 157 | " for direction_volume in direction_volumes:\n", 158 | " if ':' not in direction_volume:\n", 159 | " continue\n", 160 | " direction, volume = direction_volume.split(':')\n", 161 | " volume = int(volume.strip())\n", 162 | " direction = direction.lower()\n", 163 | " if 'north' in direction:\n", 164 | " record['vehicle volume north'] = volume\n", 165 | " elif 'south' in direction:\n", 166 | " record['vehicle volume south'] = volume\n", 167 | " elif 'west' in direction:\n", 168 | " record['vehicle volume west'] = volume\n", 169 | " elif 'east' in direction:\n", 170 | " record['vehicle volume east'] = volume\n", 171 | " return record\n", 172 | "\n", 173 | "# Convert date format and split vehicle volume field by direction\n", 174 | "traffic = traffic.map(reformat_date).map(split_vehicle_volume)\n", 175 | "\n", 176 | "# Map field names and types\n", 177 | "traffic = traffic.apply_mapping([\n", 178 | " ('id', 'long', 'id', 'long'),\n", 179 | " ('traffic volume count location address', 'string', 'address', 'string'),\n", 180 | " ('street', 'string', 'street', 'string'),\n", 181 | " ('date of count', 'string', 'date_of_count', 'date'),\n", 182 | " ('total passing vehicle volume', 'long', 'total_passing_vehicle_volume', 'long'),\n", 183 | " ('vehicle volume north', 'int', 'vehicle_volume_north', 'long'),\n", 184 | " ('vehicle volume south', 'int', 'vehicle_volume_south', 'long'),\n", 185 | " ('vehicle volume west', 'int', 'vehicle_volume_west', 'long'),\n", 186 | " ('vehicle volume east', 'int', 'vehicle_volume_east', 'long'),\n", 187 | " ('latitude', 'double', 'latitude', 'double'),\n", 188 | " ('longitude', 'double', 'longitude', 'double'),\n", 189 | " ('zip codes', 'long', 'zip_codes', 'long'),\n", 190 | "])" 191 | ] 192 | }, 193 | { 194 | "cell_type": "markdown", 195 | "metadata": {}, 196 | "source": [ 197 | "## Write data to Redshift" 198 | ] 199 | }, 200 | { 201 | "cell_type": "code", 202 | "execution_count": 104, 203 | "metadata": {}, 204 | "outputs": [ 205 | { 206 | "data": { 207 | "application/vnd.jupyter.widget-view+json": { 208 | "model_id": "", 209 | "version_major": 2, 210 | "version_minor": 0 211 | }, 212 | "text/plain": [ 213 | "FloatProgress(value=0.0, bar_style='info', description='Progress:', layout=Layout(height='25px', width='50%'),…" 214 | ] 215 | }, 216 | "metadata": {}, 217 | "output_type": "display_data" 218 | } 219 | ], 220 | "source": [ 221 | "glueContext.write_dynamic_frame.from_jdbc_conf(frame=traffic,\n", 222 | " catalog_connection='redshift',\n", 223 | " connection_options={'dbtable': 'traffic', 'database': 'dev'},\n", 224 | " redshift_tmp_dir='s3://rk-analytics-sandbox/temp-dir/'\n", 225 | ")" 226 | ] 227 | }, 228 | { 229 | "cell_type": "code", 230 | "execution_count": null, 231 | "metadata": {}, 232 | "outputs": [], 233 | "source": [] 234 | } 235 | ], 236 | "metadata": { 237 | "kernelspec": { 238 | "display_name": "Sparkmagic (PySpark)", 239 | "language": "", 240 | "name": "pysparkkernel" 241 | }, 242 | "language_info": { 243 | "codemirror_mode": { 244 | "name": "python", 245 | "version": 3 246 | }, 247 | "mimetype": "text/x-python", 248 | "name": "pyspark", 249 | "pygments_lexer": "python3" 250 | } 251 | }, 252 | "nbformat": 4, 253 | "nbformat_minor": 4 254 | } 255 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | --------------------------------------------------------------------------------